Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-SystemWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/frankxai/starlight-intelligence-system/org-role-design)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/org-role-design"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/org-role-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/org-role-design"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/org-role-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.02342 |
| Opus 5 | $0.00029 | $0.01171 |
| Sonnet 5 | $0.00012 | $0.00468 |
| Haiku 4.5 | $0.00006 | $0.00234 |
Grade A, and why
org-role-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/org-role-design
Load SIP.md, VOICES.md, agents/starlight-org.md, skills/people-intelligence/org-architecture.md. If a Genius Profile or Vision Architecture exists, load and reference. Produce a Role Architecture document. Hand off to exactly one next command.
Disclaimer (non-waivable)
This is structural thinking architecture, not employment-law advice. Role design implicates compensation, classification (exempt/non-exempt, contractor/employee), and protected-class considerations that vary by jurisdiction. Real decisions require qualified employment counsel.
Input
$ARGUMENTS
Flags
--scope <ic|manager|director|exec|founder>— what tier of role this is. Determines decision-rights complexity and span considerations.--current-state <new|ambiguous|broken|growing>:new— role doesn't exist yet; designing greenfieldambiguous— role exists but no one (including the role-holder) is clear on decision rights or accountabilitiesbroken— role exists with clear failure mode (political conflict, dropped balls, persistent performance issues that aren't a person problem)growing— role is outgrowing its design; current holder is succeeding but the role itself needs to expand or split
Process
-
Disclaim. Open with non-waivable employment-law disclaimer.
-
Locate. Confirm role title, scope, current state. If ambiguous or broken, gather inputs: who currently fills the role (if anyone), what conflicts/escalations have surfaced, what adjacent roles exist.
-
Vision-fit check. Does this role serve the 3-year horizon, or just the current quarter? If only the current quarter, name it explicitly — the role may need to be designed for outgrowing within 12-18 months, which is a different design.
-
Decision rights matrix. For the load-bearing decisions this role touches, name explicitly:
- Decides — role-holder makes the call, others informed
- Recommends — role-holder analyzes and recommends; another named role decides
- Consulted — must be asked before another role decides
- Informed — notified after decision is made
- Escalates — under condition X, the decision moves up to named role Y This is not RACI in name only. It is decision-by-decision specificity.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 178 lines · 58 tokens per session scan A 0025283bd67f
org-role-design is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 2,342 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
memories
View and manage learned memories.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.
learn
Add new learning to memory.
gbu-retro
Post-session retrospective — harvest this session's lessons into durable doctrine.
consolidate
Write a compact checkpoint summary of the current frontier.